mcpField
E
explore

explore

github.com/terrylicaDevelopment280 installsUpdated 2d ago
Repository

About explore

GitNexus Explore is a CLI-oriented skill for tracing execution flows and understanding unfamiliar code through the GitNexus knowledge graph. It guides developers from checking the index to inspecting symbols and source files, then synthesizing how a subsystem works.

Key features

  1. 01Check GitNexus index freshness
  2. 02Search ranked execution flows
  3. 03Inspect symbol callers and callees
  4. 04View source alongside symbol context
  5. 05Synthesize subsystem explanations

Use cases

  1. 01Trace how a feature executes
  2. 02Explore an unfamiliar subsystem
  3. 03Understand dependencies before code changes

MCP support

The skill explicitly states that no MCP server exists and directs users to use the GitNexus CLI, not `gitnexus://` MCP resources.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/terrylica/cc-skills --skill explore

After installing, type/explorein Claude Code to confirm it loaded.

Details

From the project README

GitNexus Explore

CLI ONLY — no MCP server exists. Never use readMcpResource with gitnexus:// URIs.

Trace execution flows and understand how code works using the GitNexus knowledge graph.

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

When to Use

  • "How does X work?"
  • "What's the execution flow for Y?"
  • "Walk me through the Z subsystem"
  • Exploring unfamiliar code areas before making changes

Workflow

Step 0: Pre-flight — Ensure CLI Is Callable

The gitnexus binary is installed via npm/mise. The mise shim may fail if node isn't active in the current project. Run this pre-flight before any gitnexus command:

# Test if gitnexus is actually callable (not just a broken shim)
gitnexus --version 2>/dev/null || mise use [email protected]

All commands below run from the repo root. If multiple repos are indexed in the workspace, add --repo <repo-name> to specify the target. Otherwise --repo is optional.

Step 1: Auto-Reindex If Stale
gitnexus status

If stale (indexed commit ≠ HEAD), automatically reindex before proceeding — do not ask the user:

gitnexus analyze

Then re-check status to confirm index is current.

Step 2: Find Execution Flows
gitnexus query "<concept>" --limit 5

This returns ranked execution flows (process chains) related to the concept.

Step 3: Get 360° Symbol View

For each relevant symbol found:

gitnexus context "<symbol>" --content

This shows:

  • Callers — who calls this symbol
  • Callees — what this symbol calls
  • Processes — execution flows this symbol participates in
  • Source — the actual code (with --content)

If multiple candidates are returned, disambiguate with:

gitnexus context "<symbol>" --uid "<full-uid>" --content
# or
gitnexus context "<symbol>" --file "<file-path>" --content
Step 4: Read Source Files

Use the Read tool to examine source files at the line numbers identified by GitNexus.

Step 5: Synthesize

Present a clear explanation covering:

  • What it is — purpose and responsibility
  • Execution flows — how data moves through the system
  • Dependencies — what it depends on, what depends on it
  • Key files — the most important files to understand

Example

User: "How does the kintsugi gap repair work?"

gitnexus query "kintsugi gap repair" --limit 5
gitnexus context "KintsugiReconciler" --content
gitnexus context "discover_shards" --content

Then read the relevant source files and synthesize the explanation.

Post-Execution Reflection

After this skill completes, reflect before closing the task:

  1. Locate yourself. — Find this SKILL.md's canonical path before editing.
  2. What failed? — Fix the instruction that caused it.
  3. What worked better than expected? — Promote to recommended practice.
  4. What drifted? — Fix any script, reference, or dependency that no longer matches reality.
  5. Log it. — Evolution-log entry with trigger, fix, and evidence.

Do NOT defer. The next invocation inherits whatever you leave behind.

Comments

Markdown supported